Journal Articles (All Issues)

Abstract

Energy harvesting plays a crucial role in extending the lifespan of wireless sensor networks deployed in unattended environments such as forest fire detection and flood detection. While solar radiation stands as the most abundant energy source, its reliability is affected by seasonal fluctuations. Consequently, a dependable solar radiation forecast becomes imperative for enhanced network planning and architecture. Utilizing statistical time series for short-term predictions in energy-harvested wireless sensor networks proves to be a swift and reliable approach. To validate the results, the NREL database is employed, and various statistical time series methods, including AR, ARMA, SARIMA, and Holt Winter, are compared based on RMSE, accuracy, and MAE. The simulations are conducted using the Python framework. This paper presents a 48-hour prediction horizon for each season, allowing for the observation of the model's effectiveness. All simulation results indicate that Holt Winter with the damped additive trend and additive seasonality outperforms other models in terms of accuracy, RMSE, and rapid response.

References

[1] S. Dhillon, C. Madhu, D. Kaur, and S. Singh, “A Solar Energy Forecast Model Using Neural Networks : Application for Prediction of Power for Wireless Sensor Networks in Precision Agriculture,” Wirel. Pers. Commun., no. 0123456789, 2020, doi: 10.1007/s11277-020-07173-w. [2] A. Kansal, J. Hsu, S. Zahedi, and M. B. Srivastava, “Power management in energy harvesting sensor networks,” ACM Trans. Embed. Comput. Syst., vol. 6, no. 4, pp. 32-es, 2007, doi: 10.1145/1274858.1274870. [3] A. Cammarano, C. Petrioli, and D. Spenza, “Pro-Energy: A novel energy prediction model for solar and wind energy-harvesting wireless sensor networks,” MASS 2012 - 9th IEEE Int. Conf. Mob. Ad-Hoc Sens. Syst., pp. 75–83, 2012, doi: 10.1109/MASS.2012.6502504. [4] H. K. Qureshi, U. Saleem, M. Saleem, A. Pitsillides, and M. Lestas, “Harvested Energy Prediction Schemes for Wireless Sensor Networks : Performance Evaluation and Enhancements,” vol. 2017, 2017. [5] G. Reikard, “Predicting solar radiation at high resolutions: A comparison of time series forecasts,” Sol. Energy, vol. 83, no. 3, pp. 342–349, 2009, doi: https://doi.org/10.1016/j.solener.2008.08.007. [6] G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time series analysis: forecasting and control. John Wiley & Sons, 2015. [7] D. Yang, P. Jirutitijaroen, and W. M. Walsh, “Hourly solar irradiance time series forecasting using cloud cover index,” Sol. Energy, vol. 86, no. 12, pp. 3531–3543, 2012, doi: 10.1016/j.solener.2012.07.029. [8] I. Colak, M. Yesilbudak, N. Genc, and R. Bayindir, “Multi-period prediction of solar radiation using ARMA and ARIMA models,” Proc. - 2015 IEEE 14th Int. Conf. Mach. Learn. Appl. ICMLA 2015, pp. 1045–1049, 2016, doi: 10.1109/ICMLA.2015.33. [9] V. Prema and K. Uma Rao, “Development of statistical time series models for solar power prediction,” Renew. Energy, vol. 83, pp. 100–109, 2015, doi: 10.1016/j.renene.2015.03.038. [10] M. H. Alsharif, M. K. Younes, and J. Kim, “Time series ARIMA model for prediction of daily and monthly average global solar radiation: The case study of Seoul, South Korea,” Symmetry (Basel)., vol. 11, no. 2, pp. 1–17, 2019, doi: 10.3390/sym11020240. [11] A. Shadab, S. Said, and S. Ahmad, “Box–Jenkins multiplicative ARIMA modeling for prediction of solar radiation: a case study,” Int. J. Energy Water Resour., vol. 3, no. 4, pp. 305–318, 2019, doi: 10.1007/s42108-019-00037-5. [12] S. Atique, S. Noureen, V. Roy, V. Subburaj, S. Bayne, and J. MacFie, “Forecasting of total daily solar energy generation using ARIMA: A case study,” 2019 IEEE 9th Annu. Comput. Commun. Work. Conf. CCWC 2019, pp. 114–119, 2019, doi: 10.1109/CCWC.2019.8666481. [13] A. Shadab, S. Ahmad, and S. Said, “Spatial forecasting of solar radiation using ARIMA model,” Remote Sens. Appl. Soc. Environ., vol. 20, p. 100427, 2020, doi: 10.1016/j.rsase.2020.100427. [14] B. Belmahdi, M. Louzazni, and A. El Bouardi, “A hybrid ARIMA–ANN method to forecast daily global solar radiation in three different cities in Morocco,” Eur. Phys. J. Plus, vol. 135, no. 11, 2020, doi: 10.1140/epjp/s13360-020-00920-9. [15] M. Jaihuni et al., “A partially amended hybrid Bi-Gru—ARIMA model (PAHM) for predicting solar irradiance in short and very-short terms,” Energies, vol. 13, no. 2, 2020, doi: 10.3390/en13020435. [16] H. Sharadga, S. Hajimirza, and R. S. Balog, “Time series forecasting of solar power generation for large-scale photovoltaic plants,” Renew. Energy, vol. 150, pp. 797–807, 2020, doi: 10.1016/j.renene.2019.12.131. [17] M. Heydari, H. Benisi Ghadim, M. Rashidi, and M. Noori, “Application of Holt-Winters Time Series Models for Predicting Climatic Parameters (Case Study: Robat Garah-Bil Station, Iran),” Polish J. Environ. Stud., vol. 29, no. 1, pp. 617–627, 2020, doi: 10.15244/pjoes/100496. [18] A. Sharma and A. Kakkar, “Forecasting daily global solar irradiance generation using machine learning,” Renew. Sustain. Energy Rev., no. May, pp. 0–1, 2017, doi: 10.1016/j.rser.2017.08.066.